Development of Privacy-preserving Deep Learning Model with Homomorphic Encryption: A Technical Feasibility Study in Kidney CT Imaging
Radiology: Artificial Intelligence · 01.11.2025 · 7 (6)
DOI: 10.1148/ryai.240798 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology: Artificial Intelligence, erschienen am 01.11.2025. Verfasst von Sang-Wook Lee und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology and Pain Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Tomography, X-Ray Computed, Computer Security, Kidney Neoplasms. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 20 Literaturangaben. Gefördert von: Asan Institute for Life Sciences, National IT Industry Promotion Agency, National Research Foundation of Korea.
Abstract (Originalsprache)
Homomorphic encryption can be integrated into deep learning models for CT-based kidney mass classification, achieving diagnostic performance similar to that of nonencrypted models while ensuring privacy protection, although with increased storage and processing time demands.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Anesthesiology and Pain Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
- CryptoLab, Seoul, Republic of Korea.
- Department of Mathematics, Yale University, New Haven, Conn.
- Department of Urology, Asan Medical Center, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, 05505 Seoul, Republic of Korea.
ORCID-Profile: Soo-Heang Eo, Garam Lee, Jungyo Suh
Förderung
- Asan Institute for Life Sciences
- National IT Industry Promotion Agency
- National Research Foundation of Korea
Zitieren
APA
Lee, S. W., Choi, J., Park, M. J., Kim, H., Eo, S. H., Lee, G., Kim, S., & Suh, J. (2025). Development of Privacy-preserving Deep Learning Model with Homomorphic Encryption: A Technical Feasibility Study in Kidney CT Imaging. Radiology: Artificial Intelligence, 7(6). https://doi.org/10.1148/ryai.240798
Vancouver
Lee SW, Choi J, Park MJ, Kim H, Eo SH, Lee G, et al. Development of Privacy-preserving Deep Learning Model with Homomorphic Encryption: A Technical Feasibility Study in Kidney CT Imaging. Radiology: Artificial Intelligence. 2025;7(6). doi:10.1148/ryai.240798
BibTeX
@article{Lee2025,
author = {Lee, Sang-Wook and Choi, Jongmin and Park, Min-Je and Kim, Hajin and Eo, Soo-Heang and Lee, Garam and Kim, Sulgi and Suh, Jungyo},
title = {Development of Privacy-preserving Deep Learning Model with Homomorphic Encryption: A Technical Feasibility Study in Kidney CT Imaging},
journal = {Radiology: Artificial Intelligence},
year = {2025},
volume = {7},
number = {6},
doi = {10.1148/ryai.240798}
}
EUVIMED